Mathematical Models for Local Nontexture Inpaintings

By Jianhong Shen, Tony F. Chan. 2002

1,302 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Semantic Image Inpainting with Deep Generative Models (2016, background): “For example, total variation (TV) based approaches [34, 1] take into account the smoothness property of natural images, which is useful to fill small missing regions or remove spurious noise.”
Image Compression With Edge-Based Inpainting (2007, methodology): “Subsequently, more models are introduced and investigated in image inpainting, e.g., total variation (TV) model [ 16 ], coupled second order PDE model taking into account the gradient orientations [17], curvature-driven diffusion (CDD) model [18], and so on. All these approaches work at pixel level ”
Split Bregman Methods and Frame Based Image Restoration (2009, methodology): “The first one is the variational or PDE based method [2, 29, 30].”
Digital inpainting based on the Mumford–Shah–Euler image model (2002, methodology): “Shen [ 10 ]. In [10], it was introduced as an alternative to the TV inpainting model.”
Image Inpainting Using Nonlocal Texture Matching and Nonlinear Filtering (2019, methodology): “Other diffusionbased image inpainting methods [4]–[10] reconstruct images”
Primal‐dual active set methods for Allen–Cahn variational inequalities with nonlocal constraints (2010, background): “For an overview and a comparison of the most common mathematical models for local non-texture image inpainting the reader is referred to [33, 18].”
Robust Image Completion via Deep Feature Transformations (2019, background): “For example, total variation (TV) based approaches [59], [60] take into consideration the smoothness property of natural images that are useful for filling small missing regions or remove spurious noise.”
A framelet-based image inpainting algorithm (2008, methodology): “It flrst transforms the current guess into the framelet domain, then performs thresholding and transforms it back to the image domain; and flnally the pixels belonging to ⁄ are replaced by the known data g on ⁄ to get a better approximation of f. The algorithm is e‐cient and gives 2 to 3 dB improvem”
Variable Exponent, Linear Growth Functionals in Image Restoration (2006, background): “6) also has direct application in image processing, as it can be used for image interpolation [13, 27], also referred to as noise-free image inpainting [8, 17, 18].”
RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments (2018, methodology): “Early approaches included diﬀusion-based texture synthesis methods [1, 5, 7], where the target area is ﬁlled by extending the surrounding textures in a coarse to ﬁne manner.”
Semantic Image Inpainting with Perceptual and Contextual Losses (2016, background): “Total variation approaches take into account of the smoothness of a natural image, which enables small holes and spurious noises to be removed [22].”